© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4330
    Prev
    Next
    INDEX
    Explanations

    text related to personal experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding an event or decision

    np_acts-logits-general · gemini-2.0-flash

    unexpected inspiration or decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.58
     demain
    -0.56
     tomorrow
    -0.55
    Портали
    -0.52
    EndContext
    -0.51
     comples
    -0.50
    明日
    -0.49
     Agamemnon
    -0.49
    TestingModule
    -0.49
    rove
    -0.48
    POSITIVE LOGITS
    たまたま
    0.90
     chanced
    0.81
    偶然
    0.80
     inspired
    0.80
     spurred
    0.76
     idea
    0.73
     Zufall
    0.72
     случайно
    0.71
    Inspired
    0.71
     fortu
    0.70
    Activations Density 0.428%

    No Known Activations